# Phase Aberration Correction without Reference Data: An Adaptive Mixed Loss Deep Learning Approach

arXiv: https://arxiv.org/abs/2303.05747 · HTML: https://mlsanity.com/paper/2303.05747/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 37 references that are in the map.
- First posted on arXiv 10 Mar 2023.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [A Deep Learning Framework for Single-Sided Sound Speed Inversion in Medical Ultrasound](https://mlsanity.com/paper/1810.00322/) (2018)
- [Bi-Directional Semi-Supervised Training of Convolutional Neural Networks for Ultrasound Elastography Displacement Estimation](https://mlsanity.com/paper/2201.13340/) (2022)
- [Speckle2Speckle: Unsupervised Learning of Ultrasound Speckle Filtering Without Clean Data](https://mlsanity.com/paper/2208.00402/) (2022)
- [Investigating Pulse-Echo Sound Speed Estimation in Breast Ultrasound with Deep Learning](https://mlsanity.com/paper/2302.03064/) (2023)
- [Ultrasound Aberration Correction based on Local Speed-of-Sound Map Estimation](https://mlsanity.com/paper/1909.10254/) (2019)
- [The SVD Beamformer: Physical Principles and Application to Ultrafast Adaptive Ultrasound](https://mlsanity.com/paper/1910.05795/) (2019)
- [Ultrasound Matrix Imaging-Part II: The distortion matrix for aberration correction over multiple isoplanatic patches](https://mlsanity.com/paper/2103.02036/) (2021)
- [An Ultra-Fast Method for Simulation of Realistic Ultrasound Images](https://mlsanity.com/paper/2109.10353/) (2021)
- [Phase Aberration Robust Beamformer for Planewave US Using Self-Supervised Learning](https://mlsanity.com/paper/2202.08262/) (2022)

## Built on by (most cited first, 1 of 1)

- [Adaptive Real-Time Multi-Loss Function Optimization Using Dynamic Memory Fusion Framework: A Case Study on Breast Cancer Segmentation](https://mlsanity.com/paper/2410.19745/) (2024)

## Abstract (arXiv)

Phase aberration is one of the primary sources of image quality degradation in ultrasound, which is induced by spatial variations in sound speed across the heterogeneous medium. This effect disrupts transmitted waves and prevents coherent summation of echo signals, resulting in suboptimal image quality. In real experiments, obtaining non-aberrated ground truths can be extremely challenging, if not infeasible. It hinders the performance of deep learning-based phase aberration correction techniques due to sole reliance on simulated data and the presence of domain shift between simulated and experimental data. Here, for the first time, we propose a deep learning-based method that does not require reference data to compensate for the phase aberration effect. We train a network wherein both input and target output are randomly aberrated radio frequency (RF) data. Moreover, we demonstrate that a conventional loss function such as mean square error is inadequate for training the network to achieve optimal performance. Instead, we propose an adaptive mixed loss function that employs both B-mode and RF data, resulting in more efficient convergence and enhanced performance. Source code is available at urlhttp://code.sonography.ai.